
# Lliberies
import pandas as pd
import plotly.figure_factory as ff

# carreguem dataset
X = pd.read_csv("penguins_size_culmen.csv")

# exploració preliminar:
print ("Resum de la estructura del dataset:\n\n")

print(X.info())
print(X.head(5))
print(X.tail(5))

Resum de la estructura del dataset:


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 342 entries, 0 to 341
Data columns (total 2 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   culmen_length_mm  342 non-null    float64
 1   culmen_depth_mm   342 non-null    float64
dtypes: float64(2)
memory usage: 5.5 KB
None
   culmen_length_mm  culmen_depth_mm
0              39.1             18.7
1              39.5             17.4
2              40.3             18.0
3              36.7             19.3
4              39.3             20.6
     culmen_length_mm  culmen_depth_mm
337              47.2             13.7
338              46.8             14.3
339              50.4             15.7
340              45.2             14.8
341              49.9             16.1


fig = ff.create_dendrogram(X, color_threshold=15)
fig.update_layout(width=1000, height=800)
fig.show()


fig = ff.create_dendrogram(X, orientation='left', color_threshold=15)

fig.update_layout(width=800, height=2000)
fig.show()

PAC 2: Estudi de tècniques de visualització de dades¶